Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A sequential neural network model for diabetes prediction.

J Park1, D W Edington

  • 1The University of Michigan, 1027 E. Huron, Ann Arbor, MI 48104-1688, USA. kddum@umich.edu

Artificial Intelligence in Medicine
|November 13, 2001
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Measurement of dijet azimuthal decorrelations at central rapidities in pp collisions at sqrt s =1.96 TeV.

Physical review letters·2005
Same author

Evaluation of the VIDAS Listeria (LIS) immunoassay for the detection of Listeria in foods using demi-Fraser and Fraser enrichment broths, as modification of AOAC Official Method 999.06 (AOAC Official Method 2004.06).

Journal of AOAC International·2005
Same author

Effects of tautomycetin on proliferation and fibronectin secretion in vascular smooth muscle cells and glomerular mesangial cells.

Transplantation proceedings·2005
Same author

Deuteron and antideuteron production in Au+Au collisions at square root of s(NN)=200 GeV.

Physical review letters·2005
Same author

Measurement of the WW production cross section in pp collisions at square root[s]=1.96 TeV.

Physical review letters·2005
Same author

Search for anomalous heavy-flavor quark production in association with W bosons.

Physical review letters·2005
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

This study developed a neural network model for diabetes prediction using health risk appraisals. The model accurately predicts diabetes risk over time, improving disease prevention strategies.

Area of Science:

  • * Computational epidemiology
  • * Predictive modeling in healthcare

Background:

  • * Existing Health Risk Appraisal (HRA) tools require evaluation for predictive accuracy over time.
  • * Diabetes prediction models need to account for time-varying risk factors and individual prognostic processes.

Purpose of the Study:

  • * To develop and evaluate a neural network (NN) model for diabetes prediction using longitudinal HRA data.
  • * To assess the model's ability to capture time-sensitive associations between risk factors and diabetes onset.
  • * To compare the NN model's performance against traditional classification and regression models.

Main Methods:

  • * Utilized a sequential multi-layered perceptron (SMLP) with backpropagation learning.
  • * Incorporated time-varying inputs and a multivariate logistic function for sequential probability prediction.

Related Experiment Videos

  • * Analyzed repeatedly measured HRAs from 6142 participants over a 3-year period (1996-1998).

    • Main Results:

    • * The SMLP model demonstrated superior performance compared to baseline models.
    • * Achieved an average profit gain of 0.18 and a sensitivity of 86.04% on test data.
    • * Successfully captured the time-sensitive nature of diabetes risk factor prediction.

    Conclusions:

    • * The developed NN model offers a time-sensitive approach for diabetes risk prediction.
    • * Findings support the implementation of proactive, time-sensitive disease prevention and management programs.
    • * This predictive framework can enhance individual prognostic assessments for diabetes.